Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    commentary or reviews of movies or shows

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.35
    /***
    -0.81
    ⓧ
    -0.77
     intersper
    -0.75
     ratify
    -0.73
     /**
    -0.73
     inaugurate
    -0.72
     defray
    -0.70
     springfox
    -0.70
    
    -0.68
    POSITIVE LOGITS
     âgé
    0.84
     originaire
    0.79
     soulign
    0.72
     épu
    0.71
     jouant
    0.69
     récomp
    0.68
     createSlice
    0.67
     bosco
    0.67
     espri
    0.67
     marié
    0.67
    Act Density 1.850%

    No Known Activations